Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kimi Work

kimi.com

Post reply on HN
Print view View original

201–210 of 305 posts

Re: Kimi Work

#201

Post by nl »

godwinson__4-8 wrote: post #195
crystal_revenge wrote: post #180

Earlier quoted context omitted.

This comment is a great example of how large and strange the skills gap in AI is right now. Curious why your first impulse is not simply to point your favorite agent at a few examples and start brainstorming/planning from there? Multiple times I’ve built a purpose specific bespoke tool starting this way. In fact, it’s a great way to learn how specialized tools are built.

The problem of the sota models clamping down on third party harnesses should be stated upfront. Getting a SOTA model in a custom harness requires API pricing or risking an account ban, correct? This preliminary change in cost may not make it worth it for people depending on which is their "favorite agent". Especially as the default harnesses for said agents continue to improve...

> Getting a SOTA model in a custom harness requires API pricing or risking an account ban, correct?

No, only Anthropic has that policy (and I think even that is relaxed for an unknown period if you use the Claude Agent SDK: https://support.claude.com/en/articles/15036540-use-the-clau...).

OpenAI, Kimi, Qwen, GLM and Deepseek all allow it.

I'm not sure about Gemini.

Re: Kimi Work

#202

Post by ashishb »

questionableans wrote: post #123
ashishb wrote: post #56

Earlier quoted context omitted.

> The repo you’re working on, sure. But all files? Yes, any tool, including any coding agent, has access to all files $USER has access to. Sandbox it explicitly to give access to only the current directory - https://github.com/ashishb/amazing-sandbox

Sorry, I meant that’s not desirable behavior that the user might expect. I understand that coding agent tools tend to play fast and loose with access because it’s not their own privacy/security at stake.

This is true for all CLI tools on Mac and Linux (and other operating systems from that era).

Historically, everything you ran was trustworthy.

Android and iOS were invented in an era that does not allow this because the risks became evident by then.

Re: Kimi Work

#203

Post by anon373839 »

gruez wrote: post #29
postalcoder wrote: post #25

kimi has been particularly shameless in copying codex 1:1, wow. Like, I get it, before condex there was conductor and a ton of other guis but this looks like they just copied the code. Also, their privacy disclosure is incredibly misleading: > How does Kimi Work protect my privacy when accessing local files? You have absolute control over your files. The built-in Ask before acting safeguard means Kimi will prompt you…

>They fail to mention that is has unfettered read access to your files. Isn't that totally expected of a coding agent? Otherwise it's like complaining dropbox "has unfettered access to your files".

It is, but I really think this project would be better as open source. They are already all-in on open for the most valuable part (the frontier model)! They might as well make the harness fully transparent so that questions about what's being accessed and transmitted can be avoided.

I personally wouldn't use any agentic harness from any company, American, Chinese, or otherwise, that is closed source. The Grok fiasco shows why.

Re: Kimi Work

#204

Post by Loocid »

timothyduong wrote: post #162
m3kw9 wrote: post #19

It rubs me the wrong way that they have to copy everything, the UI is almost exact copy of Codex. The entire mind set of just copy the best is holding them back.

Give them time, they'll work out their (Chinese UI/UX) groove just like they're working out EVs in the Chinese market. Copy first, improve and adjust later.

I hope they don't bring Chinese UI/UX to it. Native Chinese apps are a mess from a western perspective.

Re: Kimi Work

#205

Post by behohippy »

jascha_eng wrote: post #173
CookieCrisp wrote: post #160

Earlier quoted context omitted.

I highly recommend to anyone that uses them a lot - try to clone your own. I’ve got mine fully formed into how I want it, with features I haven’t seen anywhere else yet and with integration into everything I work with. We’ve lived in a world where every app had to fit enough people well enough - but now we live in a world where an app can be molded to be absolutely perfect for just you!

How did you build your own coding agent? What language/framework did you use?

It's pretty simple nowadays if you know conceptually how they work. Running the LLM calls in a loop with tools is an agent. You only need 10 or so basic tools to accomplish nearly anything, and you can build a dynamic skill system from that. Look at https://github.com/patw/pengy, ignore the app look at the spec.md file, feed that to your current agent of choice and make your own version. Use whatever tech stack or UI you're comfortable with. Change some of the choices in how it works, so it fits what you want to work.

Re: Kimi Work

#206

Post by literallywho »

sixtyj wrote: post #111
aliasxneo wrote: post #103

Has anyone cancelled their $200 ChatGPT subscription and started using Kimi? It'd be an interesting metric to measure. I for one have no motivation to use this model. Nonetheless, I'm always happy to see more competition.

There should be a benchmark re Tiananmen Square and Uyghurs among LLMs. Grok answered, ChatGPT answered, Claude answered. Chinese Z.ai replied “Content Security Warning: The input text data may contain inappropriate content“. So it is nice that Kimi is cheaper but for what price?

I've been subbing to Claude for 2 years and somehow the questions of whatever happened in Tiananmen (I know already anyway) have never once came up, but Claude (especially Fable) is now famous for refusing to work on things people want. And even pushed back against me when I was doing asking to research some people famous (infamous) in Israel-Palestine conflict. I really don't get why these "chinese gotchas" are keep coming up in every thread, they are mostly entirely inconsequential to getting actual work stuff done while same can't be said about Fable or others. Once, Gemini refused to help me make an infographic about women in STEM because the specific woman I was doing research about has died a few years ago, other models had no such qualms. All these "gotchas" are quite arbitrary.

Re: Kimi Work

#207

Post by nerdsniper »

ajross wrote: post #141
stusmall wrote: post #138

Earlier quoted context omitted.

If you remove the word "AI" from your post it also describes the last 20 or so years of US/Chinese economic competition. They are real, serious competitor but also there is a lot of value in that last 10%. Some buyers need the best and you can charge a premium for it. The speed in which a copier can catch up to a leader is faster than every before, but everything is faster these days. I think the threat is if can the…

> the last 20 or so years of US/Chinese economic competition Only with some industries, mostly electronics and light manufacturing. The rest of the history of software products doesn't look like this at all. China cloned Amazon and Meta fairly well (but only within their local/captured markets) but not Microsoft or Google and absolutely not Apple. Entertainment and culture exports are still effectively zero (like, wh…

> Heavy industry is mixed, with decent success in consumer vehicles now but little purchase in stuff like heavy equipment or shipbuilding

Uhh, China does over half of the world’s shipbuilding.

China is also responsible for 25% [1] of the world’s heavy equipment manufacturing and is considered to have double[2] the CAGR of the global average for heavy equipment manufacturing.

0: https://www.csis.org/analysis/china-dominates-shipbuilding-i...

1: https://www.grandviewresearch.com/horizon/outlook/constructi...

2: https://www.grandviewresearch.com/industry-analysis/heavy-co...

Re: Kimi Work

#208

Post by sara011 »

I feel that Kimi’s overall design is quite similar to Codex, and I hope it can excel over Codex in certain functional aspects.

Re: Kimi Work

#209

Post by cadamsdotcom »

wxw wrote: post #80

> Kimi Work is a Local Agent designed for deep workflows. It mounts your local folders, navigates the web autonomously via WebBridge, runs Python code in the background, and executes scheduled tasks. It's clearly a dupe of Claude/Codex products (Codex especially, styling-wise), but I think Kimi's goal here is simply to appear on feature-parity with bigger labs. I doubt they'd want to invest much into designing a UI f…

Some paradigms are simply ergonomic. Sometimes there's only one UX people will accept.

No one would buy a car steered with pedals; even if that is better (hey planes do it!) - every car maker is "copying" steering wheels and putting them on their cars. Is it controversial? If not why not?

Re: Kimi Work

#210

Post by ericpauley »

mrinterweb wrote: post #28
kvisner wrote: post #24

I wish they had some kind of US hosted option, NDR policy, or something like that. I love the price and power, but I have concerns around data sovereignty and leaking IP to an overseas company.

As soon as the K3 weights are published on July 27th, there will be many US providers hosting the model. I realize model hosting doesn't really apply to kimi work specifically, but in terms of accessing K3, there will be US options likely in 7 days. Just look at OpenRouter to see the providers hosting K2.6 https://openrouter.ai/moonshotai/kimi-k2.6 .

Looking at these pages reminds me of browsing jellybean components on DigiKey. Amazing for the consumer, but one does wonder: What are all these DotAI infra companies’ plans to justify any of their valuations if they’re just selling commodity compute on OpenRouter?
Post reply on HN